Download (381 KB)
Abstract: This thesis describes a new framework for parametric shape recognition. The key result is a method for generating classifiers in the form of conditional probability densities for recognizing an unknown from a set of reference models. Our procedure is automatic. Off-line, it invokes an autonomous process to estimate reference model parameters and their statistics. On-line, during measurement, it combines these with a priori context-dependent information, as well as the parameters and statistics estimated for an unknown object, into a conditional probability density function, which represents the belief in the assertion that the unknown is a particular reference model. Consequently, the method also permits the assessment of the beliefs associated with a set of assertions based on data acquired from a particular viewpoint. The importance of this result is that it provides a basis by which an external agent can assess the quality of the information from a particular viewpoint, and make informed decisions as to what action to take using the data at hand.
The thesis also describes the implementation of this procedure in a system for automatically generating and recognizing 3D part-oriented models. We show that recognition performance is near perfect for cases in which complete surface information is accessible to the algorithm, and that it falls off gracefully when only partial information is available. This leads to a sequential recognition strategy in which evidence is accumulated over successive viewpoints (at the level of the belief distribution) until a definitive assertion can be made. Experimental results are presented showing how the resulting algorithms can be used to distinguish between informative and uninformative viewpoints, rank a sequence of images on the basis of their information (e.g. to generate a set of characteristic views), and sequentially identify an unknown object.